Are Loss Functions All the Same?
From MaRDI portal
Publication:4832479
DOI10.1162/089976604773135104zbMath1089.68109OpenAlexW2034365297WikidataQ34311744 ScholiaQ34311744MaRDI QIDQ4832479
Alessandro Verri, Lorenzo Rosasco, Michele Piana, Ernesto De Vito, Andrea Caponnetto
Publication date: 4 January 2005
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/089976604773135104
Related Items (25)
On the need for structure modelling in sequence prediction ⋮ Learning rates of kernel-based robust classification ⋮ Genuinely distributed Byzantine machine learning ⋮ Local Rademacher complexity: sharper risk bounds with and without unlabeled samples ⋮ The learning rate of \(l_2\)-coefficient regularized classification with strong loss ⋮ Optimizing predictive precision in imbalanced datasets for actionable revenue change prediction ⋮ Levenberg-Marquardt multi-classification using hinge loss function ⋮ A random block-coordinate Douglas-Rachford splitting method with low computational complexity for binary logistic regression ⋮ Optimal shrinkage estimation of predictive densities under \(\alpha\)-divergences ⋮ Tensor networks in machine learning ⋮ Good edit similarity learning by loss minimization ⋮ Nonasymptotic analysis of robust regression with modified Huber's loss ⋮ Dropout training for SVMs with data augmentation ⋮ Selection dynamics for deep neural networks ⋮ SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming ⋮ A statistical learning assessment of Huber regression ⋮ Analysis of Regression Algorithms with Unbounded Sampling ⋮ Analysis of support vector machines regression ⋮ Risk-sensitive loss functions for sparse multi-category classification problems ⋮ Accelerate stochastic subgradient method by leveraging local growth condition ⋮ Unnamed Item ⋮ Incremental proximal gradient scheme with penalization for constrained composite convex optimization problems ⋮ A Framework of Learning Through Empirical Gain Maximization ⋮ An efficient primal dual prox method for non-smooth optimization ⋮ Functional linear regression with Huber loss
Cites Work
- Best choices for regularization parameters in learning theory: on the bias-variance problem.
- The covering number in learning theory
- Regularization networks and support vector machines
- On the mathematical foundations of learning
- Theory of Reproducing Kernels
- Statistical properties and adaptive tuning of support vector machines
This page was built for publication: Are Loss Functions All the Same?
